Tokenization & Preprocessing
ScrapeGraphAI/toonify
Toonify: Compact data format reducing LLM token usage by 30-60%
Pythonno licenseupdated Feb 6, 2026
🏆 #54 overall#3 of 148 in Tokenization & Preprocessing
toon-format /toon
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
$ git clone https://github.com/toon-format/toon.gitStars
25.4K
25,419
Forks
1.1K
1,123
Language
TypeScript
License
MIT
Created
Oct 22, 2025
0.9 years old
Last push
Sep 3, 2026
Categories
GitHub topics
More in Tokenization & Preprocessing
Tokenization & Preprocessing
marcelroed/gigatoken
Language model tokenization at GB/s
🧠 Natural Language Processing
RustMITupdated Sep 2, 2026
Tokenization & Preprocessing
AgentOps-AI/tokencost
Easy token price estimates for 400+ LLMs. TokenOps.
🤖 Language Models
PythonMITupdated Sep 5, 2025
Tokenization & Preprocessing
ImadSaddik/Train_Your_Language_Model_Course
Train a language model to chat like you using your personal conversations from WhatsApp, Telegram, Signal, or other platforms.
Jupyter Notebookno licenseupdated Sep 26, 2025
Tokenization & Preprocessing
alpkeskin/gotoon
Token-Oriented Object Notation for Go – JSON for LLMs at half the token cost
GoMITupdated Nov 24, 2025
Tokenization & Preprocessing
ash-01xor/bpe.c
Simple Byte pair Encoding mechanism used for tokenization process . written purely in C
CMITupdated Nov 11, 2024
Data from GitHub · snapshot Sep 24, 2026